Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23634
    Prev
    Next
    INDEX
    Explanations

    comp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חשוב
    -0.09
     PDF
    -0.08
    omis
    -0.08
     Toujours
    -0.08
     einger
    -0.08
     هزار
    -0.07
    雷
    -0.07
     Yii
    -0.07
     중요한
    -0.07
     Obama
    -0.07
    POSITIVE LOGITS
    isk
    0.08
     lowest
    0.08
     unpredict
    0.08
     sympat
    0.08
     fastest
    0.08
     //.
    0.07
    0.07
    িকে
    0.07
     wear
    0.07
    Lowest
    0.07
    Activations Density 0.001%

    No Known Activations